Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 365 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.1016. Min Act: -0.0002

Data Index: 169299 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0951. Min Act: -0.0002

Data Index: 11903 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.1022. Min Act: -0.0002

Data Index: 608740 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0971. Min Act: -0.0002

Data Index: 1006069 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0920. Min Act: -0.0002

Data Index: 367180 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0938. Min Act: -0.0002

Data Index: 1646646 (Python Code)

Max Activating Token Index: 351

Text #6

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.1055. Min Act: -0.0002

Data Index: 185065 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0834. Min Act: -0.0002

Data Index: 182194 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0903. Min Act: -0.0002

Data Index: 697018 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0916. Min Act: -0.0002

Data Index: 841565 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0892. Min Act: -0.0002

Data Index: 1365333 (Python Code)

Max Activating Token Index: 320

Text #11

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0879. Min Act: -0.0002

Data Index: 226329 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0846. Min Act: -0.0002

Data Index: 508986 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0808. Min Act: -0.0002

Data Index: 791133 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0879. Min Act: -0.0002

Data Index: 496554 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0877. Min Act: -0.0002

Data Index: 725163 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1030571 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0869. Min Act: -0.0002

Data Index: 765039 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0853. Min Act: -0.0002

Data Index: 944887 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0833. Min Act: -0.0002

Data Index: 1238648 (C4 (Web Text))

Max Activating Token Index: 198